From 010efc9b814b433bc60353caec185d905688a32b Mon Sep 17 00:00:00 2001 From: Andrew Dolgov Date: Tue, 5 Jun 2012 21:52:21 +0400 Subject: Revert "remove htmlpurifier" This reverts commit c21a462d52bd32737c32c29b060da03b38f1c2e6. --- .../library/HTMLPurifier/AttrDef/URI/Email.php | 17 ++++ .../HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php | 21 +++++ .../library/HTMLPurifier/AttrDef/URI/Host.php | 101 +++++++++++++++++++++ .../library/HTMLPurifier/AttrDef/URI/IPv4.php | 39 ++++++++ .../library/HTMLPurifier/AttrDef/URI/IPv6.php | 99 ++++++++++++++++++++ 5 files changed, 277 insertions(+) create mode 100644 lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.php create mode 100644 lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php create mode 100644 lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php create mode 100644 lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.php create mode 100644 lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.php (limited to 'lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI') diff --git a/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.php b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.php new file mode 100644 index 000000000..bfee9d166 --- /dev/null +++ b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Email.php @@ -0,0 +1,17 @@ +" + // that needs more percent encoding to be done + if ($string == '') return false; + $string = trim($string); + $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); + return $result ? $string : false; + } + +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php new file mode 100644 index 000000000..125decb2d --- /dev/null +++ b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/Host.php @@ -0,0 +1,101 @@ +ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); + $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); + } + + public function validate($string, $config, $context) { + $length = strlen($string); + // empty hostname is OK; it's usually semantically equivalent: + // the default host as defined by a URI scheme is used: + // + // If the URI scheme defines a default for host, then that + // default applies when the host subcomponent is undefined + // or when the registered name is empty (zero length). + if ($string === '') return ''; + if ($length > 1 && $string[0] === '[' && $string[$length-1] === ']') { + //IPv6 + $ip = substr($string, 1, $length - 2); + $valid = $this->ipv6->validate($ip, $config, $context); + if ($valid === false) return false; + return '['. $valid . ']'; + } + + // need to do checks on unusual encodings too + $ipv4 = $this->ipv4->validate($string, $config, $context); + if ($ipv4 !== false) return $ipv4; + + // A regular domain name. + + // This doesn't match I18N domain names, but we don't have proper IRI support, + // so force users to insert Punycode. + + // The productions describing this are: + $a = '[a-z]'; // alpha + $an = '[a-z0-9]'; // alphanum + $and = '[a-z0-9-]'; // alphanum | "-" + // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum + $domainlabel = "$an($and*$an)?"; + // toplabel = alpha | alpha *( alphanum | "-" ) alphanum + $toplabel = "$a($and*$an)?"; + // hostname = *( domainlabel "." ) toplabel [ "." ] + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + + // If we have Net_IDNA2 support, we can support IRIs by + // punycoding them. (This is the most portable thing to do, + // since otherwise we have to assume browsers support + + if ($config->get('Core.EnableIDNA')) { + $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); + // we need to encode each period separately + $parts = explode('.', $string); + try { + $new_parts = array(); + foreach ($parts as $part) { + $encodable = false; + for ($i = 0, $c = strlen($part); $i < $c; $i++) { + if (ord($part[$i]) > 0x7a) { + $encodable = true; + break; + } + } + if (!$encodable) { + $new_parts[] = $part; + } else { + $new_parts[] = $idna->encode($part); + } + } + $string = implode('.', $new_parts); + if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { + return $string; + } + } catch (Exception $e) { + // XXX error reporting + } + } + + return false; + } + +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.php b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.php new file mode 100644 index 000000000..ec4cf591b --- /dev/null +++ b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv4.php @@ -0,0 +1,39 @@ +ip4) $this->_loadRegex(); + + if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) + { + return $aIP; + } + + return false; + + } + + /** + * Lazy load function to prevent regex from being stuffed in + * cache. + */ + protected function _loadRegex() { + $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 + $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; + } + +} + +// vim: et sw=4 sts=4 diff --git a/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.php b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.php new file mode 100644 index 000000000..9454e9be5 --- /dev/null +++ b/lib/htmlpurifier/library/HTMLPurifier/AttrDef/URI/IPv6.php @@ -0,0 +1,99 @@ +ip4) $this->_loadRegex(); + + $original = $aIP; + + $hex = '[0-9a-fA-F]'; + $blk = '(?:' . $hex . '{1,4})'; + $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 + + // prefix check + if (strpos($aIP, '/') !== false) + { + if (preg_match('#' . $pre . '$#s', $aIP, $find)) + { + $aIP = substr($aIP, 0, 0-strlen($find[0])); + unset($find); + } + else + { + return false; + } + } + + // IPv4-compatiblity check + if (preg_match('#(?<=:'.')' . $this->ip4 . '$#s', $aIP, $find)) + { + $aIP = substr($aIP, 0, 0-strlen($find[0])); + $ip = explode('.', $find[0]); + $ip = array_map('dechex', $ip); + $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; + unset($find, $ip); + } + + // compression check + $aIP = explode('::', $aIP); + $c = count($aIP); + if ($c > 2) + { + return false; + } + elseif ($c == 2) + { + list($first, $second) = $aIP; + $first = explode(':', $first); + $second = explode(':', $second); + + if (count($first) + count($second) > 8) + { + return false; + } + + while(count($first) < 8) + { + array_push($first, '0'); + } + + array_splice($first, 8 - count($second), 8, $second); + $aIP = $first; + unset($first,$second); + } + else + { + $aIP = explode(':', $aIP[0]); + } + $c = count($aIP); + + if ($c != 8) + { + return false; + } + + // All the pieces should be 16-bit hex strings. Are they? + foreach ($aIP as $piece) + { + if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) + { + return false; + } + } + + return $original; + + } + +} + +// vim: et sw=4 sts=4 -- cgit v1.2.3